Aiming at the characteristics of strong coupling,underactuated,nonlinear and so on,and the problems of being easily interfered in the actual flight process of the quad-rotor Unmanned Aerial Vehicle(UAV),the dynamics model of the quad-rotor UAV was analyzed,and an attitude control algorithm of the quad-rotor UAV based on sliding mode-Credit Points Cerebellar Model Articulation Controller(CPCMAC)was proposed.On this basis,the semi-physical simulation system of the quad-rotor UAV was designed.Firstly,the sliding mode controller is designed for the nonlinear system,with position control rate and attitude control rate tailored to tracking track and roll angle.Secondly,as practical application of sliding mode controller can produce oscillation,a cerebellar neural network based on credit integral is employed to learn the sliding mode control.Finally,a LabVIEW-based control station is established for data transmission and transmission control with Matlab/Simulink.Simulation results demonstrate that compared with traditional Proportional Integral Derivative(PID)control and integral backstepping method control,proposed sliding mode-CPCMAC joint controll for the quad-rotor UAV has significant advantages in suppressing overshoot and residual while being superior in rapidity and robustness.Meanwhile,built quad-rotor UAV semi-physical simulation platform provides clear feedback on changes of UAV parameters;reserved parameter interface application along with ground control station reduces development difficulty of UAV flight-control algorithm thereby improving development efficiency having obvious practical value.
关键词
无人机/小脑模型神经网络/滑模控制/半物理仿真/风场
Key words
unmanned aerial vehicle/cerebellar model articulation controller/sliding mode control/semi-physical simulation/wind field
维普
万方数据